Update app.py

app.py

@@ -2,13 +2,18 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from huggingface_hub import InferenceClient
 
+# Environment variable for HF token
+hf_token = "os.environ.get("HF_TOKEN")"
+
+# Your model ID
 model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=hf_token)
 
+# Load the model
+model = AutoModelForCausalLM.from_pretrained(model_id, use_auth_token=hf_token, device_map="auto")
 
-                                             
 def format_prompt(message, history):
   prompt = "<s>"
   for user_prompt, bot_response in history: